CUDA: Week in Review
Mon., October 10, 2011, Issue #63 - Newsletter Home
Welcome to CUDA: Week in Review, an online news summary for the worldwide CUDA, GPU computing and parallel programming ecosystem.
William Putman, NASA
October Webinar Lineup
Ecosystem Update
Awards and Recognitions
CUDA on the Web
Sign up to be a CUDA Registered Developer
Follow @GPUComputing on Twitter
CUDA Spotlight
GPU-Accelerated Climate Simulation
This week’s Spotlight is on William Putman, a NASA research meteorologist in the Global Modeling and Assimilation Office (GMAO) in the Earth Sciences Division of Goddard Space Flight Center’s Sciences and Exploration Directorate. Here’s an extract from our interview:
Matt Thompson, Bill Putman, Max Suarez
NVIDIA: Bill, what does your group do?
Bill: Our research and development activities aim to maximize the impact of satellite observations in climate, weather and atmospheric composition prediction using comprehensive global models and data assimilation.

To achieve this goal, the GMAO develops models and assimilation systems for the atmosphere, ocean, and land surface, generates products to support NASA instrument teams and the NASA Earth Science program, and undertakes scientific research to inform system development pathways.

Within the GMAO we have a group of developers (Dr. Max Suarez, Dr. Matthew Thompson and myself) tasked with the restructuring of NASA’s Goddard Earth Observing System atmospheric general circulation model version 5 (GEOS-5) to take advantage of new accelerator technologies including GPUs.
NVIDIA: What are the benefits of using CUDA?
Bill: The Portland Group (PGI) offers us an opportunity to explicitly program for GPUs using CUDA Fortran and also provides a directive-based accelerator model. GEOS-5 is primarily written in Fortran, thus the PGI CUDA Fortran syntax allows us to develop GPU kernels in GEOS-5 using a familiar coding environment.

Like CUDA C, CUDA Fortran allows for low-level management of the initialization, data transfer, and coding details of a project without the need to translate legacy Fortran code into C. This aids both in speed of development and with keeping a readable (to developers) codebase within GEOS-5 while achieving much the same performance as CUDA C.
  - Read the complete interview here

  (Would you like to be in the CUDA Spotlight? Email
CUDA Developer News
Check Out the October CUDA Webinar Lineup! back to the top
Tues., Oct. 11: PGI Accelerator for C - Simplified GPU Programming Using Directives
            Presented by Dr. Michael Wolfe, The Portland Group

Tues., Oct. 11: CUDA Optimization: Memory Bandwidth Limited Kernels + Live Q&A
            Presented by Tim Schroeder, NVIDIA

Wed., Oct. 12: Intro to Parallel Nsight and Features (Preview of Version 2.1)
            Presented by Shane Evans, NVIDIA

Thurs., Oct 20: Overview and Usage of LibJacket CUDA Library
            Presented by James Malcolm, AccelerEyes (with NVIDIA)

Thurs., Oct. 27: GPU Computing with MATLAB
            Presented by Sarah Wait Zaranek, MathWorks
Ecosystem Update
Rogue Wave Software, provider of cross-platform software development tools, announced the release of TotalView 8.9.2 with support for CUDA 4.0:

Awards and Recognitions
The Johns Hopkins University has been named a CUDA Center of Excellence, recognizing its ground-breaking work leveraging GPU computing. As a CCOE, Johns Hopkins will utilize equipment and grants provided by NVIDIA to support a number of research and academic programs, including deployment of the "Data-Scope," a GPU-powered, ultra-high throughput supercomputer to dramatically increase the speed of scientific data analysis:

Boise State University, a CUDA Research Center, received two grants that build on GPU computing initiatives:
- NOAA Field Research Office collaboration to develop a CUDA Fortran version of NOAA’s HYSPLIT
  Air Dispersion model:
- NSF CAREER Grant for multi-scale modeling of short-term forecasting and grid integration of
  wind energy:

This year’s PRACE (Partnership for Advanced Computing in Europe) Award goes to a paper titled "Astrophysical Particle Simulations with Large Custom GPU Clusters on Three Continents". Prof. Richard Kenway, Chairman of the PRACE Scientific Steering Committee, noted that "the work points the way to exploit exascale technologies for problems at the forefront of science."

CUDA on the Web
A new video on "Volt: Interactive Volume Rendering with CUDA" has been posted by the Computer Graphics Lab at the Bonn-Rhine-Sieg University of Applied Sciences. Volt is an interactive direct volume renderer that takes advantage of GPUs for high quality interactive ray casting.

The Irish Center for High-End Computing (ICHEC) launched a new website dedicated to GPU computing. ICHEC’s Director, Prof. James Slevin, said: "Computer simulation has now reached a level of predictability that firmly grounds its impact and importance along with theory and experimentation as the third pillar of science research."

Industrial Mathematics KTN released a new report on "The GPU Computing Revolution: from Multi-Core CPUs to Many-Core Graphics Processors." Produced in collaboration with the London Mathematical Society, it was written by Simon McIntosh-Smith of the University of Bristol.
Replays of the Week
GPUs Storm into Climate Simulations, by Will Park
back to the top
Inner Geek - Project GT90 Supercar, by Adam Pintek
Replays of the Week
NEW: Each week we highlight a session from GTC 2010. Here is our pick for this week: back to the top
            Rapid Prototyping using Thrust: High Performance Dosimetry (GTC 10)
            Guillaume Saupin - CEA, France
NEW: AIR, a provider of risk modeling software, is seeking a Senior Software Engineer in Boston, Mass. Responsibilities include contributing to development of next-generation HPC-based analytical framework, algorithms and tooling (using C++,C#, SQL and CUDA).
- Apply online:
back to the top
HPC & GPU SupercomputingKudos to the South Florida GPU Meetup, organized by Adnan Boz, for designing a clever logo based on a fish swarm. The group recently held its third Meetup, where Adnan presented on "Thinking in Parallel."

Feel free to attend upcoming GPU Meetups. The atmosphere is casual and collaborative. Participants and sponsors are warmly welcomed.

- US
        Silicon Valley GPU Meetup – Oct. 10, 6:15 pm
        New Mexico GPU Meetup – Oct. 15, 5:00 pm
        New York GPU Meetup – Oct. 24, 6:00 pm (Special joint meeting with
        C++ Dev Group)
        South Florida GPU Meetup – Oct. 24, 6:30 pm

- Australia
        Sydney GPU Meetup – Oct. 13, 6:00 pm
        Melbourne GPU Meetup – Oct. 19, 5:30 pm
        Brisbane GPU Meetup – Oct. 20, 6:00 pm
GTC Asia 2011 (Dec. 14-15)
Poster deadline: Nov 3

GTC U.S. 2012 (May 14-17)
Session deadline: Nov. 3
Poster deadline: Dec. 8

Bioinformatics: BICoB 2012 (March 12-14)
Paper deadline: Oct. 28
CUDA Calendar
October 2011 back to the top
- NEW: PGI Accelerator for C - Simplified GPU Programming Using Directives (Webinar)
Oct. 11, 2011
Presented by Dr. Michael Wolfe, The Portland Group

- NEW: CUDA Optimization: Memory Bandwidth Limited Kernels + Live Q&A (Webinar)
Oct. 11, 2011
Presented by Tim Schroeder, NVIDIA

- NEW: Intro to Parallel Nsight and Features (Webinar)
Oct. 12, 2011
Presented by Shane Evans, NVIDIA

- CUDA 4-Day Training Course - Acceleware
Oct. 11-14, 2011, Los Angeles, Calif.
Presented by Acceleware with Microsoft

- GPU-Accelerated Derivative Pricing Models — SciComp
Oct. 17, 2011, London, UK
Presented by SciComp, NVIDIA, Dell, Microsoft

- NEW: Overview and Usage of LibJacket CUDA Library – AccelerEyes (Webinar)
Oct 20, 2011
Presented by James Malcolm, AccelerEyes (with NVIDIA)

- GPU Computing with MATLAB (Webinar)
Oct. 27, 2011
Presented by Sarah Wait Zaranek, MathWorks

November 2011

- CUDA 4-Day Training Course — Acceleware
Nov. 1-4, 2011, Frankfurt, Germany
Presented by Acceleware with Microsoft

- Supercomputing 2011 (SC11)
Nov. 12-18, Seattle, Washington

- GPU Programming for Defense/Intelligence — AccelerEyes (Webinar)
Nov. 15, 2011
Learn to accelerate common defense and intelligence algorithms using easy, powerful programming libraries, with Jacket for use with MATLAB and LibJacket for C/C++/Fortran.

- CUDA Training (Basic and Advanced) — CAPS
Nov. 22-24, 2011, Rennes, France
Email: training (at)

December 2011

- AGU (American Geophysical Union) Meeting
Dec. 5, 2011, San Francisco
Session on High-Res Modeling Using GPU and Many-Core Architectures

- NEW: Intro to GPU Programming Workshop - La Maison de la Simulation
Dec. 5-9, 2011, France

- GTC Asia
Dec. 14-15, 2011, Beijing, China
Featuring the latest GPU computing breakthroughs, demos and presentations.

- LibJacket CUDA Library for Maximus — AccelerEyes (Webinar)
Dec. 15, 2011
Learn to integrate computations with visualizations in a CUDA-based app through simple visualization functions for plotting, image and volume rendering, and more.

(To list an event, email:

CUDA Resources
Tesla MD SimCluster back to the top
– Tesla MD SimCluster:
– CUDA 4.0:
– Parallel Nsight:
– Parallel Nsight:
CUDA Registered Developer Program
– Sign up:
– List of CUDA-enabled GPUs:
CUDA on the Web
– See previous issues of CUDA: Week in Review:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
– Check out the NVIDIA Research page:
CUDA Recommended Reading
– Future of Computing Performance:
– Supercomputing for the Masses, Part 21:
– CUDA books:
CUDA Recommended Viewing
– The Third Pillar of Science:
– GTC 2010 presentations:
– SC10 presentations:
About CUDA
CUDA is NVIDIA’s parallel computing hardware architecture. NVIDIA provides a complete toolkit for programming on the CUDA architecture, supporting standard computing languages such as C, C++ and Fortran as well as APIs such as OpenCL and DirectCompute. Send comments and suggestions to:
You are receiving this email because you have previously expressed interest in NVIDIA products and technologies. Click here to opt in specifically to CUDA: Week in Review. NVIDIA

Copyright © 2011 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.